data task

library(readr)
library(tidyverse)
library(stargazer)
library(fixest)
library(kableExtra)
library(plotly)


setwd("E:/data/mkt")

#1-1
obesity <- read.csv("obesity.csv",header=T)
obesity<-obesity[,c(1,3,6,7)]
colnames(obesity)[1]<-"country"
measured<-subset(obesity, SUBJECT=="MEASURED")
self<-subset(obesity, SUBJECT=="SELFREPORTED")
stargazer(measured,
          type = 'text', 
          digits=2, align=T,median = T,
          title = "Measured",
          keep = 'Value')

## 
## Measured
## =================================================================
## Statistic  N  Mean  St. Dev.  Min  Pctl(25) Median Pctl(75)  Max 
## -----------------------------------------------------------------
## Value     177 48.54  17.64   18.60  30.10   55.90   62.50   75.20
## -----------------------------------------------------------------

stargazer(self,
          type = 'text', 
          digits=2, align=T,median = T,
          title = "Self-reported",
          keep = 'Value')

## 
## Self-reported
## =================================================================
## Statistic  N  Mean  St. Dev.  Min  Pctl(25) Median Pctl(75)  Max 
## -----------------------------------------------------------------
## Value     348 46.34   8.71   13.00  42.00   46.80   51.60   66.60
## -----------------------------------------------------------------

OECD<-unique(obesity$country)
cpi<-read.csv("CPI.csv",header=T)
# subset annual data, prices of food, measured by annual growth rate
cpi<-subset(cpi, FREQUENCY=="A" & SUBJECT=="FOOD" & MEASURE =="AGRWTH")
cpi<-cpi[,c(1,6,7)]
colnames(cpi)[1]<-"country"
# subset OECD countries
cpi<-subset(cpi,country %in% OECD)

stargazer(cpi,
          type = 'text', 
          digits=2, align=T,median = T,
          title = "CPI",
          keep = 'Value')

## 
## CPI
## ====================================================================
## Statistic   N   Mean St. Dev.  Min   Pctl(25) Median Pctl(75)  Max  
## --------------------------------------------------------------------
## Value     1,802 7.35  24.88   -13.85   1.28    3.30    6.97   773.99
## --------------------------------------------------------------------

#1-3
obes<-aggregate(measured$Value,by=list(year=measured$TIME),mean)
colnames(obes)[2]<-"measured"
obes$measured<-round(obes$measured,0)

ggplot(obes, aes(x = year,y = measured)) +
  geom_segment( aes(x=year, xend=year, y=0, yend=measured), color="grey") +
  geom_point( color="orange", size=4) +
  theme_light() +
  theme(
    panel.grid.major.x = element_blank(),
    panel.border = element_blank(),
    axis.ticks.x = element_blank()
  ) +
  geom_text(data = obes,aes(x = year,y = measured,label =measured),nudge_y = 5, nudge_x = 0.05)+
  xlab("year") +
  ylab("average measured obesity rate(%)")

# 3
coke<-read.csv("coca.csv")[,c(1,4)]

# 3-1
colnames(cpi)[3]<-"CPI"
colnames(measured)[4]<-"obesity"

cpi2<-aggregate(cpi$CPI,by=list(year=cpi$TIME),mean)
measured2<-aggregate(measured$obesity,by=list(year=measured$TIME),mean)

colnames(cpi2)[2]<-"CPI"
colnames(measured2)[2]<-"obesity"

cpi_obesity2<-merge(cpi2, measured2, by="year")


g<-ggplot(cpi_obesity2, aes(x=CPI, y=obesity,colour=year)) + 
  geom_point()+
  theme_bw()

ggplotly(g)

# 3-2
obesity_coke<-merge(measured, na.omit(coke), by="country",all = T)
g<-ggplot(obesity_coke, aes(x=kj, y=obesity,colour=country)) + 
  geom_point()+
  theme_bw()

ggplotly(g)

# 3-3
dat<-merge(obesity_coke, cpi,by=c("country","TIME"),all=T)
dat<-na.omit(dat)

fit1 = feols(obesity~log(kj),  dat)

fit2 = feols(obesity~log(kj) | TIME, dat)

fit3 = feols(obesity~CPI , dat)

fit4 = feols(obesity~CPI | TIME, dat)

fit5 = feols(obesity~CPI | country, dat)

fit6 = feols(obesity~CPI | TIME+country, dat)

x<-etable(fit1 , fit2,fit3, fit4,fit5,fit6,
       cluster = "country", headers = c("without","time","without","time","country","time+country"))


kable(x, "html") %>%
  kable_styling(full_width = F)

	fit1	fit2	fit3	fit4	fit5	fit6
	without	time	without	time	country	time+country
Dependent Var.:	obesity	obesity	obesity	obesity	obesity	obesity
(Intercept)	2,826.2*** (439.3)		46.95*** (9.202)
log(kj)	-428.7*** (67.94)	-405.5*** (60.85)
CPI			0.3898 (1.035)	1.703 (1.360)	-0.8970** (0.2525)	-0.3275 (0.2495)
Fixed-Effects:	——————	—————–	—————-	————-	——————	—————-
TIME	No	Yes	No	Yes	No	Yes
country	No	No	No	No	Yes	Yes
_______________	__________________	_________________	________________	_____________	__________________	________________
S.E.: Clustered	by: country	by: country	by: country	by: country	by: country	by: country
Observations	170	170	170	170	170	170
R2	0.65104	0.74912	0.00474	0.30853	0.93922	0.97908
Within R2	–	0.66148	–	0.06697	0.22710	0.04688

library(xml2)
library(dplyr)
library(rvest)
website <- read_html('https://www.basspro.com/shop/en/centerfire-pistol')
guns <- website %>% html_elements("section")
guns


names <- guns %>% 
  html_nodes(".product_name a") %>% 
  html_text2()
names

prices <- guns %>% 
  html_nodes(".price span") %>% 
  html_text2()
prices